summaryrefslogtreecommitdiff
path: root/test/Transforms/SROA/vector-promotion.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/Transforms/SROA/vector-promotion.ll')
-rw-r--r--test/Transforms/SROA/vector-promotion.ll164
1 files changed, 160 insertions, 4 deletions
diff --git a/test/Transforms/SROA/vector-promotion.ll b/test/Transforms/SROA/vector-promotion.ll
index ea28f5d1a647a..02f6d040cc950 100644
--- a/test/Transforms/SROA/vector-promotion.ll
+++ b/test/Transforms/SROA/vector-promotion.ll
@@ -36,15 +36,15 @@ entry:
define i32 @test2(<4 x i32> %x, <4 x i32> %y) {
; CHECK: @test2
-; FIXME: This should be handled!
entry:
%a = alloca [2 x <4 x i32>]
-; CHECK: alloca <4 x i32>
+; CHECK-NOT: alloca
%a.x = getelementptr inbounds [2 x <4 x i32>]* %a, i64 0, i64 0
store <4 x i32> %x, <4 x i32>* %a.x
%a.y = getelementptr inbounds [2 x <4 x i32>]* %a, i64 0, i64 1
store <4 x i32> %y, <4 x i32>* %a.y
+; CHECK-NOT: store
%a.tmp1 = getelementptr inbounds [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
%tmp1 = load i32* %a.tmp1
@@ -54,10 +54,18 @@ entry:
%a.tmp3.cast = bitcast i32* %a.tmp3 to <2 x i32>*
%tmp3.vec = load <2 x i32>* %a.tmp3.cast
%tmp3 = extractelement <2 x i32> %tmp3.vec, i32 0
+; CHECK-NOT: load
+; CHECK: %[[extract1:.*]] = extractelement <4 x i32> %x, i32 2
+; CHECK-NEXT: %[[extract2:.*]] = extractelement <4 x i32> %y, i32 3
+; CHECK-NEXT: %[[extract3:.*]] = shufflevector <4 x i32> %y, <4 x i32> undef, <2 x i32> <i32 0, i32 1>
+; CHECK-NEXT: %[[extract4:.*]] = extractelement <2 x i32> %[[extract3]], i32 0
%tmp4 = add i32 %tmp1, %tmp2
%tmp5 = add i32 %tmp3, %tmp4
ret i32 %tmp5
+; CHECK-NEXT: %[[sum1:.*]] = add i32 %[[extract1]], %[[extract2]]
+; CHECK-NEXT: %[[sum2:.*]] = add i32 %[[extract4]], %[[sum1]]
+; CHECK-NEXT: ret i32 %[[sum2]]
}
define i32 @test3(<4 x i32> %x, <4 x i32> %y) {
@@ -206,6 +214,154 @@ define i64 @test6(<4 x i64> %x, <4 x i64> %y, i64 %n) {
ret i64 %res
}
+define <4 x i32> @test_subvec_store() {
+; CHECK: @test_subvec_store
+entry:
+ %a = alloca <4 x i32>
+; CHECK-NOT: alloca
+
+ %a.gep0 = getelementptr <4 x i32>* %a, i32 0, i32 0
+ %a.cast0 = bitcast i32* %a.gep0 to <2 x i32>*
+ store <2 x i32> <i32 0, i32 0>, <2 x i32>* %a.cast0
+; CHECK-NOT: store
+; CHECK: %[[insert1:.*]] = shufflevector <4 x i32> <i32 0, i32 0, i32 undef, i32 undef>, <4 x i32> undef, <4 x i32> <i32 0, i32 1, {{.*}}>
+
+ %a.gep1 = getelementptr <4 x i32>* %a, i32 0, i32 1
+ %a.cast1 = bitcast i32* %a.gep1 to <2 x i32>*
+ store <2 x i32> <i32 1, i32 1>, <2 x i32>* %a.cast1
+; CHECK-NEXT: %[[insert2:.*]] = shufflevector <4 x i32> <i32 undef, i32 1, i32 1, i32 undef>, <4 x i32> %[[insert1]], <4 x i32> <i32 4, i32 1, i32 2, {{.*}}>
+
+ %a.gep2 = getelementptr <4 x i32>* %a, i32 0, i32 2
+ %a.cast2 = bitcast i32* %a.gep2 to <2 x i32>*
+ store <2 x i32> <i32 2, i32 2>, <2 x i32>* %a.cast2
+; CHECK-NEXT: %[[insert3:.*]] = shufflevector <4 x i32> <i32 undef, i32 undef, i32 2, i32 2>, <4 x i32> %[[insert2]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
+
+ %a.gep3 = getelementptr <4 x i32>* %a, i32 0, i32 3
+ store i32 3, i32* %a.gep3
+; CHECK-NEXT: %[[insert4:.*]] = insertelement <4 x i32> %[[insert3]], i32 3, i32 3
+
+ %ret = load <4 x i32>* %a
+
+ ret <4 x i32> %ret
+; CHECK-NEXT: ret <4 x i32> %[[insert4]]
+}
+
+define <4 x i32> @test_subvec_load() {
+; CHECK: @test_subvec_load
+entry:
+ %a = alloca <4 x i32>
+; CHECK-NOT: alloca
+ store <4 x i32> <i32 0, i32 1, i32 2, i32 3>, <4 x i32>* %a
+; CHECK-NOT: store
+
+ %a.gep0 = getelementptr <4 x i32>* %a, i32 0, i32 0
+ %a.cast0 = bitcast i32* %a.gep0 to <2 x i32>*
+ %first = load <2 x i32>* %a.cast0
+; CHECK-NOT: load
+; CHECK: %[[extract1:.*]] = shufflevector <4 x i32> <i32 0, i32 1, i32 2, i32 3>, <4 x i32> undef, <2 x i32> <i32 0, i32 1>
+
+ %a.gep1 = getelementptr <4 x i32>* %a, i32 0, i32 1
+ %a.cast1 = bitcast i32* %a.gep1 to <2 x i32>*
+ %second = load <2 x i32>* %a.cast1
+; CHECK-NEXT: %[[extract2:.*]] = shufflevector <4 x i32> <i32 0, i32 1, i32 2, i32 3>, <4 x i32> undef, <2 x i32> <i32 1, i32 2>
+
+ %a.gep2 = getelementptr <4 x i32>* %a, i32 0, i32 2
+ %a.cast2 = bitcast i32* %a.gep2 to <2 x i32>*
+ %third = load <2 x i32>* %a.cast2
+; CHECK-NEXT: %[[extract3:.*]] = shufflevector <4 x i32> <i32 0, i32 1, i32 2, i32 3>, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
+
+ %tmp = shufflevector <2 x i32> %first, <2 x i32> %second, <2 x i32> <i32 0, i32 2>
+ %ret = shufflevector <2 x i32> %tmp, <2 x i32> %third, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: %[[tmp:.*]] = shufflevector <2 x i32> %[[extract1]], <2 x i32> %[[extract2]], <2 x i32> <i32 0, i32 2>
+; CHECK-NEXT: %[[ret:.*]] = shufflevector <2 x i32> %[[tmp]], <2 x i32> %[[extract3]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+
+ ret <4 x i32> %ret
+; CHECK-NEXT: ret <4 x i32> %[[ret]]
+}
+
+declare void @llvm.memset.p0i32.i32(i32* nocapture, i32, i32, i32, i1) nounwind
+
+define <4 x float> @test_subvec_memset() {
+; CHECK: @test_subvec_memset
+entry:
+ %a = alloca <4 x float>
+; CHECK-NOT: alloca
+
+ %a.gep0 = getelementptr <4 x float>* %a, i32 0, i32 0
+ %a.cast0 = bitcast float* %a.gep0 to i8*
+ call void @llvm.memset.p0i8.i32(i8* %a.cast0, i8 0, i32 8, i32 0, i1 false)
+; CHECK-NOT: store
+; CHECK: %[[insert1:.*]] = shufflevector <4 x float> <float 0.000000e+00, float 0.000000e+00, float undef, float undef>, <4 x float> undef, <4 x i32> <i32 0, i32 1, {{.*}}>
+
+ %a.gep1 = getelementptr <4 x float>* %a, i32 0, i32 1
+ %a.cast1 = bitcast float* %a.gep1 to i8*
+ call void @llvm.memset.p0i8.i32(i8* %a.cast1, i8 1, i32 8, i32 0, i1 false)
+; CHECK-NEXT: %[[insert2:.*]] = shufflevector <4 x float> <float undef, float 0x3820202020000000, float 0x3820202020000000, float undef>, <4 x float> %[[insert1]], <4 x i32> <i32 4, i32 1, i32 2, {{.*}}>
+
+ %a.gep2 = getelementptr <4 x float>* %a, i32 0, i32 2
+ %a.cast2 = bitcast float* %a.gep2 to i8*
+ call void @llvm.memset.p0i8.i32(i8* %a.cast2, i8 3, i32 8, i32 0, i1 false)
+; CHECK-NEXT: %[[insert3:.*]] = shufflevector <4 x float> <float undef, float undef, float 0x3860606060000000, float 0x3860606060000000>, <4 x float> %[[insert2]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
+
+ %a.gep3 = getelementptr <4 x float>* %a, i32 0, i32 3
+ %a.cast3 = bitcast float* %a.gep3 to i8*
+ call void @llvm.memset.p0i8.i32(i8* %a.cast3, i8 7, i32 4, i32 0, i1 false)
+; CHECK-NEXT: %[[insert4:.*]] = insertelement <4 x float> %[[insert3]], float 0x38E0E0E0E0000000, i32 3
+
+ %ret = load <4 x float>* %a
+
+ ret <4 x float> %ret
+; CHECK-NEXT: ret <4 x float> %[[insert4]]
+}
+
+define <4 x float> @test_subvec_memcpy(i8* %x, i8* %y, i8* %z, i8* %f, i8* %out) {
+; CHECK: @test_subvec_memcpy
+entry:
+ %a = alloca <4 x float>
+; CHECK-NOT: alloca
+
+ %a.gep0 = getelementptr <4 x float>* %a, i32 0, i32 0
+ %a.cast0 = bitcast float* %a.gep0 to i8*
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast0, i8* %x, i32 8, i32 0, i1 false)
+; CHECK: %[[xptr:.*]] = bitcast i8* %x to <2 x float>*
+; CHECK-NEXT: %[[x:.*]] = load <2 x float>* %[[xptr]]
+; CHECK-NEXT: %[[expand_x:.*]] = shufflevector <2 x float> %[[x]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+; CHECK-NEXT: %[[insert_x:.*]] = shufflevector <4 x float> %[[expand_x]], <4 x float> undef, <4 x i32> <i32 0, i32 1, {{.*}}>
+
+ %a.gep1 = getelementptr <4 x float>* %a, i32 0, i32 1
+ %a.cast1 = bitcast float* %a.gep1 to i8*
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast1, i8* %y, i32 8, i32 0, i1 false)
+; CHECK-NEXT: %[[yptr:.*]] = bitcast i8* %y to <2 x float>*
+; CHECK-NEXT: %[[y:.*]] = load <2 x float>* %[[yptr]]
+; CHECK-NEXT: %[[expand_y:.*]] = shufflevector <2 x float> %[[y]], <2 x float> undef, <4 x i32> <i32 undef, i32 0, i32 1, i32 undef>
+; CHECK-NEXT: %[[insert_y:.*]] = shufflevector <4 x float> %[[expand_y]], <4 x float> %[[insert_x]], <4 x i32> <i32 4, i32 1, i32 2, {{.*}}>
+
+ %a.gep2 = getelementptr <4 x float>* %a, i32 0, i32 2
+ %a.cast2 = bitcast float* %a.gep2 to i8*
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast2, i8* %z, i32 8, i32 0, i1 false)
+; CHECK-NEXT: %[[zptr:.*]] = bitcast i8* %z to <2 x float>*
+; CHECK-NEXT: %[[z:.*]] = load <2 x float>* %[[zptr]]
+; CHECK-NEXT: %[[expand_z:.*]] = shufflevector <2 x float> %[[z]], <2 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 1>
+; CHECK-NEXT: %[[insert_z:.*]] = shufflevector <4 x float> %[[expand_z]], <4 x float> %[[insert_y]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
+
+ %a.gep3 = getelementptr <4 x float>* %a, i32 0, i32 3
+ %a.cast3 = bitcast float* %a.gep3 to i8*
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast3, i8* %f, i32 4, i32 0, i1 false)
+; CHECK-NEXT: %[[fptr:.*]] = bitcast i8* %f to float*
+; CHECK-NEXT: %[[f:.*]] = load float* %[[fptr]]
+; CHECK-NEXT: %[[insert_f:.*]] = insertelement <4 x float> %[[insert_z]], float %[[f]], i32 3
+
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %a.cast2, i32 8, i32 0, i1 false)
+; CHECK-NEXT: %[[outptr:.*]] = bitcast i8* %out to <2 x float>*
+; CHECK-NEXT: %[[extract_out:.*]] = shufflevector <4 x float> %[[insert_f]], <4 x float> undef, <2 x i32> <i32 2, i32 3>
+; CHECK-NEXT: store <2 x float> %[[extract_out]], <2 x float>* %[[outptr]]
+
+ %ret = load <4 x float>* %a
+
+ ret <4 x float> %ret
+; CHECK-NEXT: ret <4 x float> %[[insert_f]]
+}
+
define i32 @PR14212() {
; CHECK: @PR14212
; This caused a crash when "splitting" the load of the i32 in order to promote
@@ -222,7 +378,7 @@ entry:
}
define <2 x i8> @PR14349.1(i32 %x) {
-; CEHCK: @PR14349.1
+; CHECK: @PR14349.1
; The first testcase for broken SROA rewriting of split integer loads and
; stores due to smaller vector loads and stores. This particular test ensures
; that we can rewrite a split store of an integer to a store of a vector.
@@ -244,7 +400,7 @@ entry:
}
define i32 @PR14349.2(<2 x i8> %x) {
-; CEHCK: @PR14349.2
+; CHECK: @PR14349.2
; The first testcase for broken SROA rewriting of split integer loads and
; stores due to smaller vector loads and stores. This particular test ensures
; that we can rewrite a split load of an integer to a load of a vector.
generated by cgit v1.2.3 (git 2.25.1) at 2025-06-10 15:06:37 +0000